System and method for automatic distribution of conversation topics

CROSS-REFERENCE TO RELATED APPLICATION

0001The present application is a continuation of U.S. patent application Ser. No. 12/705,854, filed Feb. 15, 2010, entitled “SYSTEM AND METHOD FOR AUTOMATIC DISTRIBUTION OF CONVERSATION TOPICS,” which is hereby incorporated herein by reference in its entirety.

FIELD OF THE INVENTION

0002The present invention relates generally to social networking, and in particular to automatically determining a topic in a conversation, and distributing notification of the topic to a destination.

BACKGROUND OF THE INVENTION

0003People are interested in providing summaries of their daily activities, thoughts and experiences to colleagues, family, and friends. Web sites, such as MySpace™ and Facebook enable people to easily fulfill this desire, and have proven to be extremely popular. Often, recipients of these summaries share similar interests with the individual providing the summary. In some instances, had the recipient been timely notified that the individual was engaged in a particular activity or was discussing a particular topic with another individual, the recipient may have sought to join the activity or discussion. However, it may be impractical or impossible for an individual, in a timely manner, to continually keep colleagues and friends aware of what the individual is engaged in, or what they are discussing with others.

0004Keeping friends timely notified of topics being discussed in a telephone conversation is particularly challenging. It is impractical, and potentially dangerous, for a participant of a telephone conversation to simultaneously email or text other individuals regarding the topics being discussed during the conversation. Moreover, from a logistical standpoint, it may be impossible to concurrently send and receive text messages while engaging in a voice call. Yet, it is quite common that a group of friends share a common interest, and a call between two members of the group may have been enjoyed by multiple members of the group had each of the friends been aware of the conversation while it was occurring. Thus, it would be beneficial if an individual could automatically distribute notifications of topics being discussed during a telephone conversation to desired destinations.

SUMMARY OF THE INVENTION

0005The present invention identifies a topic being discussed by participants during a voice call, and distributes a notification of the topic to one or more destinations. A recipient of the notification may be provided an opportunity to join the voice call with the approval of one or both of the participants.

0006A first participant initiates a voice call with a second participant. As the first participant speaks, a communications device used by the first participant generates an audio stream containing voice signals of the first participant. The communications device sends the audio stream toward the communications device used by the second participant. A topic identification module receives the audio stream. The audio stream is converted to a text stream, and terms are extracted from the text stream. A topic is determined based on one or more of the terms detected in the text stream. The topic identification module sends the topic to a topic distribution module. The topic distribution module distributes a topic notification identifying at least one of the participants, and the topic, to one or more destinations.

0007The topic notification may include an invitation to join the voice call. If a recipient of the topic notification accepts the invitation, an authorization request identifying the recipient may be sent to one or both of the participants. If the authorization request is granted, a communication session may be initiated with the recipient, and the recipient may be joined to the voice call.

0008Multiple topic notifications may be distributed during a voice call. The topic identification module may determine topics on a continual basis, or at desired time intervals during the voice call. The topic identification module may maintain a list of distributed topics so that multiple topic notifications regarding the same topic are not distributed.

0009The topic identification module and topic distribution module may be located in one or both of the communications devices used by the first and second participants, or in a network element in the path of the audio streams. In one embodiment, the topic identification module may be located in one or both of the communications devices, and the topic distribution module may be located in a network element. A semantic analysis of the terms may be performed to determine a topic. For example, an ontology may be used by the topic identification module to determine a topic.

0010Either or both participants may have a topic filter that includes topic criteria that identifies whether a determined topic is suitable for distribution. The topic filter may include an approved topics list identifying topics suitable for distribution and/or a disapproved topics list identifying topics unsuitable for distribution. The topic filter may also include an approved conversation participant list identifying conversation participants with whom topic notifications may be distributed, and/or a disapproved conversation participant list identifying conversation participants with whom topic notifications may not be distributed. The topic filter may further include location criteria including an approved location list identifying potential locations of a conversation from which topic notifications may be distributed, and/or a disapproved location list identifying potential locations of a conversation from which topic notifications may not be distributed. The topic filter may further include time criteria including an approved time list identifying times of conversations during which topic notifications may be distributed, and/or a disapproved time list identifying times of conversations during which topic notifications may not be distributed.

0011One or both participants may receive a topic authorization request that must be granted prior to distributing a topic notification. A participant maintains a destination distribution list identifying destinations to which topic notifications should be distributed. A destination may include a web site, a computer, a mobile phone, a social network service such as MySpace™ and Facebook, and the like. A participant may have a distribution filter that further restricts distribution of topics based on identified distribution criteria. For example, the distribution criteria may include a topic destination list identifying that only certain topics may be distributed to certain destinations. A topic notification may be distributed in a variety of different formats suitable for the identified destination, such as a web site posting, an SMS text message, an email, and the like.

0012Those skilled in the art will appreciate the scope of the present invention and realize additional aspects thereof after reading the following detailed description of the preferred embodiments in association with the accompanying drawing figures.

BRIEF DESCRIPTION OF THE DRAWING FIGURES

0013The accompanying drawing figures incorporated in and forming a part of this specification illustrate several aspects of the invention, and together with the description serve to explain the principles of the invention.

0014<figref idref="DRAWINGS">FIG. 1</figref> is a block diagram of a system illustrating aspects of the present invention;

0015<figref idref="DRAWINGS">FIG. 2</figref> is a flowchart illustrating a method for determining topics according to one embodiment of the invention;

0016<figref idref="DRAWINGS">FIG. 3</figref> is a flowchart illustrating a method for distributing a topic notification according to one embodiment of the invention;

0017<figref idref="DRAWINGS">FIG. 4</figref> is a block diagram illustrating an exemplary topic notification;

0018<figref idref="DRAWINGS">FIG. 5</figref> is a flowchart illustrating a method for joining a recipient to a voice call based on a topic notification according to one embodiment of the invention; and

0019<figref idref="DRAWINGS">FIG. 6</figref> is a block diagram of a communications device according to one embodiment of the invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

0020The embodiments set forth below represent the necessary information to enable those skilled in the art to practice the invention and illustrate the best mode of practicing the invention. Upon reading the following description in light of the accompanying drawing figures, those skilled in the art will understand the concepts of the invention and will recognize applications of these concepts not particularly addressed herein. It should be understood that these concepts and applications fall within the scope of the disclosure and the accompanying claims.

0021The present invention identifies a topic being discussed by participants during a voice call, and distributes a notification of the topic to one or more destinations. A recipient of the notification may be provided an opportunity to join the voice call with the approval of one or both of the participants.

0022<figref idref="DRAWINGS">FIG. 1</figref> illustrates a system <b>10</b> suitable for practicing aspects of the present invention. The system <b>10</b> includes a first participant <b>12</b> who uses a first communications device <b>14</b> to engage in a voice call with a second participant <b>16</b> using a second communications device <b>18</b>. The phrase “voice call” is intended to encompass a real-time communication session of a finite duration between at least two individuals, such as a telephone call, a voice over internet protocol (VoIP) call, and the like. The first communications device <b>14</b> and the second communications device <b>18</b> can comprise any suitable processing device capable of engaging in voice calls, including, for example, a PDA, a mobile phone such as a cellular phone, a laptop computer, a desktop computer and the like. Preferably, at least one of the first communications device <b>14</b> and the second communications device <b>18</b> is a mobile communications device.

0023The first communications device <b>14</b> establishes a communication session <b>20</b> with the second communications device <b>18</b> via a communications medium <b>21</b>. The communications medium <b>21</b> may comprise a wired or wireless medium such as WiFi, cellular technology, Ethernet, and the like, and may depend on a type of communications device <b>18</b>. The communication session <b>20</b> may be established using any suitable protocol or protocols, including, for example, Session Initiation Protocol, MGC, standard cellular and PSTN signaling mechanisms, and the like. The communications session <b>20</b> is typically facilitated by one or more network elements <b>22</b> that reside in a network <b>24</b>. The network element <b>22</b> can comprise a server, a switch, or any other communications device in the path, or otherwise coupled to, the communications session <b>20</b>.

0024A first audio stream <b>26</b> comprising voice signals is generated by the first communications device <b>14</b> in response to words spoken by the first participant <b>12</b>. The first audio stream <b>26</b> is provided to the communications session <b>20</b> for delivery to the second communications device <b>18</b>. Similarly, a second audio stream <b>28</b> comprising voice signals is generated by the second communications device <b>18</b> in response to words spoken by the second participant <b>16</b>. The first audio stream <b>26</b> and second audio stream <b>28</b> may comprise analog or digital signals. The network element <b>22</b> receives the first audio stream <b>26</b> and the second audio stream <b>28</b> via a communications interface <b>25</b>. The network element <b>22</b> includes a topic identification module <b>30</b> and a topic distribution module <b>32</b>, each of which is coupled to a controller <b>34</b>. The controller <b>34</b> may include a central processing unit and memory (not shown) for storing instructions suitable for implementing the functionality described herein. The topic identification module <b>30</b> detects one or more terms in the voice signals in one or both of the audio streams <b>26</b>, <b>28</b>. Terms include words spoken by either or both of the first and the second participants <b>12</b>, <b>16</b>. Based on the detected terms, the topic identification module <b>30</b> identifies a topic being discussed by the first participant <b>12</b> and the second participant <b>16</b>. The topic may be filtered based on topic filter criteria <b>36</b> contained in a memory <b>38</b>, such as a random access memory, a flash memory, a hard disk drive, and the like. A topic can comprise words describing the subject matter of the discussion based on the detected terms. For example, a topic may comprise “Star Trek movie,” “Lamborghini automobiles,” “skiing,” and the like.

0025The network element <b>22</b> can also include an emotion recognition module <b>31</b> which can analyze one or both of the audio streams <b>26</b>, <b>28</b> to detect and identify an emotional state of one or both of the first and second participants <b>12</b>, <b>16</b>. The emotion recognition module <b>31</b> may identify the detected emotion via an emotion identifier, which may be used for topic filtering purposes, or topic notification purposes, as described in greater detail herein.

0026The topic identification module <b>30</b> sends the topic to the topic distribution module <b>32</b>. The topic distribution module <b>32</b> obtains a distribution list <b>40</b> from the memory <b>38</b>, identifying potential destinations to which a topic notification may be distributed. The potential destinations may be filtered based on a distribution filter criteria <b>42</b>. User preferences maintained in the memory <b>38</b>, such as in the topic filter criteria <b>36</b>, the distribution filter criteria <b>42</b>, or user preference data <b>44</b>, may identify various additional options regarding times, locations and the like that may affect if and when a topic notification is distributed.

0027The topic distribution module <b>32</b> distributes a topic notification to a destination, such as a third communications device <b>46</b>. A recipient <b>48</b> views the topic notification on the third communications device <b>46</b>. The topic notification may include an invitation for the recipient <b>48</b> to join, or participate, in the voice call. The invitation can comprise, for example, a user actuatable link that, when actuated, indicates to the network element <b>22</b> that the recipient <b>48</b> would like to join the voice call. The network element <b>22</b> may seek approval from one or both of the first and the second participants <b>12</b>, <b>16</b>. Assuming approval is granted, the network element <b>22</b> may initiate a communication session <b>50</b> with the third communications device <b>46</b>. The network element <b>22</b> may then join the communication session <b>50</b> with the communication session <b>20</b>, and the first and the second participants <b>12</b>, <b>16</b> and the recipient <b>48</b> may converse with one another.

0028<figref idref="DRAWINGS">FIG. 2</figref> is a flowchart illustrating a method for determining topics according to one embodiment of the invention. <figref idref="DRAWINGS">FIG. 2</figref> will be discussed in conjunction with <figref idref="DRAWINGS">FIG. 1</figref>. For purposes of illustration, it will be assumed that the first participant <b>12</b> is a subscriber to a topic distribution service that implements aspects of the present invention. Thus, the discussion herein will primarily focus on the topic identification module <b>30</b> with respect to the first audio stream <b>26</b> generated by the first communications device <b>14</b> in response to voice signals of the first participant <b>12</b>. However, in practice, the second participant <b>16</b> may also be a subscriber to such a service, or otherwise have a topic identification module <b>30</b> that identifies topics from the second audio stream <b>28</b>. Where both of the first and the second participants <b>12</b>, <b>16</b> of a voice call may desire to have topic notifications distributed, the first and the second participants <b>12</b>, <b>16</b> may decide that topic notifications may be distributed without approval of either party, only with approval of one party, or only with approval of both parties. Such options may be configured by the first and the second participants <b>12</b>, <b>16</b> upon mutual agreement at the beginning of the voice call, or may be preconfigured and stored in the memory <b>38</b>. For example, the first participant <b>12</b> may have a configuration option that indicates the first participant <b>12</b> always desires to have topic notifications distributed. The second participant <b>16</b>, on the other hand, may have a configuration option that indicates topic notifications should be distributed only between 5:00 PM and 8:00 AM. If the conversation between the first participant <b>12</b> and the second participant <b>16</b> occurs at 4:00 PM, the first participant <b>12</b> may receive a message generated by the network element <b>22</b> indicating topic notifications will not be distributed based on the configuration option of the second participant <b>16</b>. Alternately, topics determined from the first audio stream <b>26</b> may be distributed based on the configuration option of the first participant <b>12</b>, while no topic notification distribution will occur based on the second audio stream <b>28</b>. It is apparent that such conflicts could be handled in a number of different ways as desired by the first and the second participants <b>12</b>, <b>16</b>, or by a service provider providing such a topic distribution service.

0029The topic identification module <b>30</b> initially obtains user preference information associated with the first participant <b>12</b> from one or more of the topic filter criteria <b>36</b>, the distribution filter criteria <b>42</b> and the user preference data <b>44</b> in the memory <b>38</b> (step <b>100</b>). The user preference information may include time criteria identifying times the first participant <b>12</b> desires topic notification distribution, or times the first participant <b>12</b> does not desire topic notification distribution. For example, the time criteria may indicate that topic notification distribution is not desired between 8:00 AM-5:00 PM Monday through Friday.

0030The user preference information may also include location criteria indicating locations from which the first participant <b>12</b> desires topic notification distribution, or locations from which the first participant <b>12</b> does not desire topic notification distribution. For example, the user preference information may indicate the first participant <b>12</b> does not desire topic notification distribution when the first participant <b>12</b> is at work. The location of the first participant <b>12</b> may be provided by the first participant <b>12</b> to the topic notification distribution service, or may be obtained by information provided by the communications device <b>14</b>, such as from a GPS module in the communications device <b>14</b>. The user preference information may also include participant criteria indicating that the first participant <b>12</b> desires topic notification distribution only when conversing with certain other participants, such as the second participant <b>16</b>. The second participant <b>16</b> may be identified by, for example, caller identification information provided during setup of the communication session <b>20</b>. If, based on any of the user preference information, the first participant <b>12</b> does not desire topic notification distribution, the topic identification module <b>30</b> terminates and does not determine topics (step <b>102</b>).

0031If the first participant <b>12</b> desires topic notification distribution, the topic identification module <b>30</b> detects terms in the voice signals of the first audio stream <b>26</b> (step <b>104</b>). Term detection may include, for example, converting the voice signals carried in the first audio stream <b>26</b> to a textual stream of words, and selecting words from the textual stream. A natural language processor may be used to identify the terms. Based on the detected terms, a topic is determined (<b>106</b>). A topic is one or more words that describe the subject matter of the voice call at a given point in time. Topic identification may be aided via semantic analysis, such as through the use of an ontology, for example. Topics may be identified based on terms detected in either the first audio stream <b>26</b>, the second audio stream <b>28</b>, or via a combination of terms detected in both the first audio stream <b>26</b> and the second audio stream <b>28</b>.

0032Topic identification may also be aided via contextual information which may be available to the topic identification module <b>30</b>, such as, for example, location information associated with the first participant <b>12</b>. For example, a new Star Trek movie may be showing in movie theaters. The topic identification module <b>30</b> may detect words such as “Captain,” “Kirk,” and “Sulu,” and, based on an ontology, conclude that the topic is “Star Trek.” The topic identification module <b>30</b> may further determine that the location of the communications device <b>14</b> is adjacent or near a movie theater showing the new Star Trek movie. The location of the communications device <b>14</b> may be obtained from the service provider providing cellular service to the communications device <b>14</b>, or via a location service to which the first participant <b>12</b> subscribes, or via other conventional means. Based on the proximity of the first participant <b>12</b> to the movie theater, the topic identification module <b>30</b> may conclude that the topic is “the new Star Trek movie” rather than merely “Star Trek.”

0033The topic may be filtered based on one or more topic filter criteria <b>36</b> (step <b>108</b>). The topic filter criteria <b>36</b> may comprise any information by which the first participant <b>12</b> may indicate whether a determined topic is suitable for distribution. For example, the topic filter criteria <b>36</b> may include an approved topics list which identifies topics approved for notification distribution by the first participant <b>12</b>. Approved topics may include, for example, topics in which the first participant <b>12</b> knows his friends or colleagues have a mutual interest. An exemplary approved topics list is provided in Table 1.

0034<tables id="TABLE-US-00001" num="00001"><table frame="none" colsep="0" rowsep="0"><tgroup align="left" colsep="0" rowsep="0" cols="2"><colspec colname="offset" colwidth="70pt" align="left" /><colspec colname="1" colwidth="147pt" align="left" /><thead><row><entry /><entry namest="offset" nameend="1" rowsep="1">TABLE 1</entry></row><row><entry /><entry namest="offset" nameend="1" align="center" rowsep="1" /></row></thead><tbody valign="top"><row><entry /><entry>movies</entry></row><row><entry /><entry>Lamborghini automobiles</entry></row><row><entry /><entry>real estate</entry></row><row><entry /><entry>Sally</entry></row><row><entry /><entry>beagles</entry></row><row><entry /><entry namest="offset" nameend="1" align="center" rowsep="1" /></row></tbody></tgroup></table></tables>

0035Alternately or additionally, the topic filter criteria <b>36</b> may include a disapproved topics list which identifies topics disapproved for notification distribution by the first participant <b>12</b>. An exemplary disapproved topics list is provided in Table 2.

0036<tables id="TABLE-US-00002" num="00002"><table frame="none" colsep="0" rowsep="0"><tgroup align="left" colsep="0" rowsep="0" cols="2"><colspec colname="offset" colwidth="77pt" align="left" /><colspec colname="1" colwidth="140pt" align="left" /><thead><row><entry /><entry namest="offset" nameend="1" rowsep="1">TABLE 2</entry></row><row><entry /><entry namest="offset" nameend="1" align="center" rowsep="1" /></row></thead><tbody valign="top"><row><entry /><entry>wife</entry></row><row><entry /><entry>boss</entry></row><row><entry /><entry>finances</entry></row><row><entry /><entry>Matt</entry></row><row><entry /><entry>EMOTION: crying</entry></row><row><entry /><entry>cooking/2</entry></row><row><entry /><entry namest="offset" nameend="1" align="center" rowsep="1" /></row></tbody></tgroup></table></tables>

0037While for purposes of illustration Tables 1 and 2 are shown as having a relatively simple list of topics, any of the filter criteria described herein, such as the approved topics list or the disapproved topics list, may further delineate categories of topics, in addition to specific topics, to which the filter criteria may be applied. For example, the disapproved topics list may include an entry such as “cooking/2,” indicating that the topic “cooking” should not be distributed, nor should any topic that is identified in the respective ontology as being within two levels of the topic “cooking.” For example, an ontology may classify a topic “roasting” as being within two levels, or nodes, of the topic “cooking.” The topic identification module may detect the topic “roasting,” but based on the entry in the disapproved topics list of “cooking/2,” determine that the topic “roasting” is a disapproved topic.

0038The network element <b>22</b> may also include the emotion recognition module <b>31</b> for detecting an emotional state that may be conveyed by the first participant <b>12</b> in the first audio stream <b>26</b>. The emotion recognition module <b>31</b> may be integral with the topic identification module <b>30</b>, or may be a separate module coupled to the topic identification module <b>30</b>. The first audio stream <b>26</b> may be provided to the topic identification module <b>30</b> and the emotion recognition module <b>31</b> serially or in parallel. Detected topics and recognized emotions may have timestamps associated therewith for purposes of determining a current emotion for purposes of filtering and generating a topic notification.

0039The emotion recognition module <b>31</b> may recognize and identify an emotion conveyed by the first participant <b>12</b> in the first audio stream <b>26</b>, such as “yelling,” “laughing,” “crying,” and the like. The emotion recognition module <b>31</b> may generate an emotion identifier identifying the recognized emotion. Emotions may be used for filtering purposes and for topic notification purposes. For example, the disapproved topics list may include an entry such as “Emotion: crying” indicating that topics should not be distributed if a “crying” emotion has been detected. While the emotion criteria is illustrated for purposes of convenience in the disapproved topic list, those skilled in the art will recognize separate topic filter criteria tables may be used for approved/disapproved emotions.

0040The emotion identifier identifying a particular emotion such as “yelling,” “laughing,” and “crying” can be provided, along with the topic, to the topic distribution module <b>32</b>. The topic distribution module <b>32</b> may use the emotion identifier to generate a topic notification that identifies the recognized emotion. For example, the topic distribution module <b>32</b> may generate a topic notification comprising “JOHN IS YELLING ABOUT THE NEW STAR TREK MOVIE TO SALLY.”

0041If the determined topic is not suitable for distribution based on the topic filter criteria <b>36</b> (step <b>110</b>), the process may end, or may resume detecting terms (step <b>112</b>). The process described herein for determining topics and distributing topic notifications may be iterative, and repeated many times during the duration of the voice call. According to one embodiment, the process repeats on a continual basis after a predetermined period of time, for example every 10 seconds. Alternatively, the process operates on a buffered audio stream after a predetermined time frame of the audio stream has been buffered. For example, two buffers may exist in the memory <b>38</b>, each capable of holding at least two minutes of the audio stream <b>26</b>. After the first buffer is full, the topic identification module <b>30</b> may examine the audio stream in the first buffer to determine topics for notification distribution. During this time, the ongoing audio stream is then buffered in the second buffer. At the end of two minutes, the topic identification module <b>30</b> may examine the audio stream in the second buffer to determine topics for notification distribution. Alternatively, the process operates on a buffered audio stream after a predetermined amount of memory is used. For example, two buffers may exist in the memory <b>38</b> of a particular size, such as 2 MB. Upon the first buffer becoming full, the topic identification module <b>30</b> may examine the audio stream in the first buffer to determine topics for notification distribution. During this period of time, the audio stream is being buffered in the second buffer. Irrespective of the precise process used, the topic identification module <b>30</b> may maintain a table of topics for which topic notifications have been distributed to prevent repeatedly distributing topic notifications on the same topic during the duration of the call.

0042If the determined topic is suitable for distribution (step <b>110</b>), then it may be determined whether topic approval by one or more of the first and the second participants <b>12</b>, <b>16</b> is required (step <b>114</b>). If not, then the topic may be provided to the topic distribution module <b>32</b> (step <b>116</b>). If topic approval is required, the topic identification module <b>30</b> may initiate a topic authorization request message to the first participant <b>12</b> identifying the topic, and requesting approval to distribute a topic notification (step <b>118</b>). The first participant <b>12</b> may be provided, for example, an SMS message with the determined topic. The first participant <b>12</b> may then reply to the message “yes” or “no” to indicate approval or to deny approval, respectively (step <b>120</b>). Alternatively, the SMS message could include two actuatable links, one of which is actuated, or selected, by the first participant <b>12</b> to indicate approval and the second of which is selected to indicate disapproval. In another embodiment, a user interface may be displayed on the communications device <b>14</b> which includes selectable controls that enable the user to easily grant approval or deny the request. If the first participant <b>12</b> does not grant approval, the process may determine whether to end the topic notification distribution process, or to resume detecting terms (step <b>112</b>). If the first participant <b>12</b> indicates approval to distribute a topic notification, the topic identification module <b>30</b> sends the topic to the topic distribution module <b>32</b> for distribution (step <b>116</b>).

0043<figref idref="DRAWINGS">FIG. 3</figref> is a flowchart illustrating a method for distributing a topic notification according to one embodiment of the present invention. The topic distribution module <b>32</b> may initially obtain the distribution list <b>40</b> from the memory <b>38</b> identifying potential destinations to which the topic may be distributed (step <b>200</b>). The potential destinations may include one or more of a web site, an email address, a telephone, or any other addressable destinations to which a topic notification can be distributed. An exemplary distribution list <b>40</b> is illustrated in Table 3.

0044<tables id="TABLE-US-00003" num="00003"><table frame="none" colsep="0" rowsep="0"><tgroup align="left" colsep="0" rowsep="0" cols="2"><colspec colname="offset" colwidth="63pt" align="left" /><colspec colname="1" colwidth="154pt" align="left" /><thead><row><entry /><entry namest="offset" nameend="1" rowsep="1">TABLE 3</entry></row><row><entry /><entry namest="offset" nameend="1" align="center" rowsep="1" /></row></thead><tbody valign="top"><row><entry /><entry>9195551212</entry></row><row><entry /><entry>www.righefd.com/post.html</entry></row><row><entry /><entry>djohnsont@wert.com</entry></row><row><entry /><entry>2075551212</entry></row><row><entry /><entry namest="offset" nameend="1" align="center" rowsep="1" /></row></tbody></tgroup></table></tables>

0045The distribution list <b>40</b> may be filtered based on distribution filter criteria <b>42</b> (step <b>202</b>). The distribution filter criteria <b>42</b> may indicate that only certain topics may be distributed to certain destinations. For example, the distribution filter criteria <b>42</b> may indicate that any topic may be posted to the www.righefd.com/post.html destination, but only “beagles” and “real estate” topics may be distributed to the “9195551212” destination. The distribution filter criteria <b>42</b> may also indicate that only certain topics may be sent to destinations that are, at the time of topic identification, at certain locations. For example, the distribution filter criteria <b>42</b> may indicate that a topic notification for the topic “beagles” may be sent to the “9195551212” destination only when the “9195551212” destination is at “home.” The location of the “9195551212” destination may be obtained by conventional mechanisms, such as, for example, information provided by a service provider that provides service to the device, or a location service to which the device is registered. A table may be maintained that cross-references location information provided by the service provider or location service with identified locations, such as “home.”

0046The topic distribution module <b>32</b> may then generate the topic notification (step <b>204</b>). The topic notification identifies the determined topic, and at least one of the first participant <b>12</b> and the second participant <b>16</b>. The topic distribution module <b>32</b> then distributes the topic notification to one or more destinations based on the distribution filter criteria <b>42</b> (<b>206</b>). The form of the topic notification may differ depending on the destination. The topic notification may take the form of a posting where the destination is a web site, and an SMS message where the destination is a telephone number, for example. The topic notification may be an email where the destination is an email address.

0047<figref idref="DRAWINGS">FIG. 4</figref> is a block diagram illustrating an exemplary topic notification and distribution. <figref idref="DRAWINGS">FIG. 4</figref> will be discussed in conjunction with <figref idref="DRAWINGS">FIG. 1</figref>. A topic notification <b>300</b> is received by the third communications device <b>46</b>, such as a mobile phone. The third communications device <b>46</b> includes a display <b>302</b>, wherein the topic notification <b>300</b> is displayed. The topic notification <b>300</b> may have been sent by SMS, for example, and therefore may comprise an SMS message. The topic notification <b>300</b> includes an identification of a topic <b>304</b>, such as, for example, the “Star Trek movie.” The topic notification <b>300</b> includes a participant identification <b>306</b>, which, in this example, identifies “John” and “Sally” as the participants to the voice call. The topic notification <b>300</b> also includes a link <b>308</b> which, if selected or otherwise actuated by the recipient <b>48</b>, indicates a desire by the recipient <b>48</b> to join the voice call between John and Sally. While for purposes of illustration the topic notification <b>300</b> is shown as an SMS message, those skilled in the art will recognize that the topic notification may comprise any desired format, and may include media in addition to text. For example, the topic notification may comprise a multimedia messaging service (MMS) message that includes an image, such as an icon, relating to the determined topic.

0048<figref idref="DRAWINGS">FIG. 5</figref> is a flowchart illustrating a method for joining a recipient to a voice call based on a topic notification according to one embodiment of the present invention. <figref idref="DRAWINGS">FIG. 5</figref> will be discussed in conjunction with <figref idref="DRAWINGS">FIGS. 1 and 4</figref>. After receiving the topic notification <b>300</b>, the recipient <b>48</b> indicates a desire to join the voice call between the first participant <b>12</b> and the second participant <b>16</b> (step <b>400</b>). The recipient <b>48</b> may indicate a desire to join, for example, by selecting the link <b>308</b> that is included in the topic notification <b>300</b>. The selection of the link <b>308</b> may indicate to the network element <b>22</b>, or any other suitable network element, that the recipient <b>48</b> wishes to join the voice call. The selection of the link <b>308</b> may identify both the voice call that the recipient <b>48</b> wishes to join, as well as the address, such as the telephone number, of the third communications device <b>46</b>. For example, referring again to <figref idref="DRAWINGS">FIG. 4</figref>, the link <b>308</b> may include metadata identifying the voice call between the first participant <b>12</b> and the second participant <b>16</b>, as well as the phone number of the third communications device <b>46</b>. Selection of the link <b>308</b> by the recipient <b>48</b> may then cause a request including the metadata to be provided to the network element <b>22</b>.

0049Upon receipt of the request, the network element <b>22</b> may initiate a notification of the request to the first participant <b>12</b> (step <b>404</b>). The notification may include a mechanism by which the first participant <b>12</b> can easily approve or disapprove of the request. For example, the notification may include two links, one of which if selected by the first participant <b>12</b> indicates an approval for the recipient <b>48</b> to join the voice call, and the second of which may indicate a disapproval for the recipient <b>48</b> to join the voice call. Assuming the first participant <b>12</b> indicates an approval to allow the recipient <b>48</b> to join the voice call, the network element <b>22</b> may initiate a communication session <b>50</b> with the third communications device <b>46</b> (<b>408</b>). Once the communication session <b>50</b> is established, the network element <b>22</b> may then merge the communication session <b>50</b> with the communication session <b>20</b> to enable the first participant <b>12</b>, the second participant <b>16</b> and the recipient <b>48</b> to converse with each other (step <b>410</b>).

0050While the topic identification module <b>30</b> and the topic distribution module <b>32</b> have been described herein as being in the network element <b>22</b>, the topic identification module <b>30</b> may be in one or both of the communications devices <b>14</b>, <b>18</b>. Similarly, the topic distribution module <b>32</b> could also be in one or both of the communications devices <b>14</b>, <b>18</b>. In one embodiment, the topic identification module <b>30</b> is located in one or both of the communications devices <b>14</b>, <b>18</b>, and the topic distribution module <b>32</b> is located in the network element <b>22</b>. Thus, elements of the present invention may be distributed, as desired, between communications devices and network elements. Moreover, while the functionality associated with aspects of the present invention have been, for purposes of illustration, described as being provided in multiple modules, such as the topic identification module <b>30</b> and the topic distribution module <b>32</b>, such functionality could be provided in a single module, or in more than two modules, as desired.

0051The invention has been described herein in the context of an ongoing voice call. However, the invention may be implemented even shortly after the termination of a voice call, or during the session termination process terminating the voice call. For example, all or a portion of the audio streams <b>26</b>, <b>28</b> may be buffered in a memory, and the topic identification module <b>30</b> may detect terms from the buffered audio streams <b>26</b>, <b>28</b> and determine a topic even as the voice call is terminated, or shortly thereafter. Other aspects of the invention would operate as described herein, except in such embodiment, a recipient will not be provided an opportunity to join the call.

0052<figref idref="DRAWINGS">FIG. 6</figref> is a block diagram of the communications device <b>14</b> according to one embodiment of the invention. The communications device <b>14</b> includes a controller <b>500</b> that includes a central processing unit (CPU) <b>502</b> and a memory <b>504</b>, such as a random access memory, that may contain software instructions <b>506</b> suitable for providing the functionality described herein for determining topics and distributing notifications of the topics. The communications device <b>14</b> may also include a communications interface <b>508</b> adapted to interface with the network <b>24</b>.

0053Various aspects of the present invention may be embodied in instructions that are stored in hardware, and may reside, for example, on a computer program product such as a flash memory, in Random Access Memory (RAM), flash memory, Read Only Memory (ROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), registers, hard disk, a removable disk, a CD-ROM, or any other form of computer readable or computer usable storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC.

0054Those skilled in the art will recognize improvements and modifications to the preferred embodiments of the present invention. All such improvements and modifications are considered within the scope of the concepts disclosed herein and the claims that follow.